© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107650
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owell
    -0.29
     incumb
    -0.28
    utt
    -0.25
    OSC
    -0.25
     Butt
    -0.25
    cheap
    -0.25
    åıªæĺ¯ä¸Ģ个
    -0.25
    oles
    -0.25
    æ¢Ń
    -0.25
    icamente
    -0.24
    POSITIVE LOGITS
    terms
    0.25
    -<?
    0.24
    -theme
    0.24
    elize
    0.23
    æĪļ
    0.23
    åİĦ
    0.23
     offsets
    0.23
    ech
    0.23
    drm
    0.22
     Css
    0.22
    Activations Density 6.240%

    No Known Activations

    This feature has no known activations.